Research map / 3D vision / Human pose estimation
CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation
Zhihao Li, Jianzhuang Liu, Zhensong Zhang, Songcen Xu, Youliang Yan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add bounding box input (CI) (ablation) | CLIFF · Human3.6M | MPJPE: 84.0 -> 81.4 | Improved |
| add bounding box input (CI) (ablation) | CLIFF · Human3.6M | PA-MPJPE: 52.4 -> 52.1 | Improved |
| add full-frame reprojection loss (CS) (ablation) | CLIFF w/o CI · Human3.6M | MPJPE: 85.2 -> 84.0 | Improved |
| add full-frame reprojection loss (CS) (ablation) | CLIFF w/o CI · Human3.6M | PA-MPJPE: 54.5 -> 52.4 | Improved |
| use CLIFF as base model of the annotator instead of HMR (ablation) | pseudo-GT annotator · 3DPW | MPJPE: 63.6 -> 52.8 | Improved |
| use CLIFF as base model of the annotator instead of HMR (ablation) | pseudo-GT annotator · 3DPW | PVE: 72.6 -> 61.5 | Improved |
| replace EFT pseudo-GT with CLIFF annotator pseudo-GT for COCO training | CLIFF trained on COCO · 3DPW | MPJPE: 98.8 -> 85.4 | Improved |
| replace SPIN pseudo-GT with CLIFF annotator pseudo-GT for COCO training | CLIFF trained on COCO · Human3.6M | MPJPE: 115.0 -> 96.1 | Improved |
| replace HMR-EFT baseline with CLIFF (Res-50) | HMR-EFT · 3DPW | MPJPE: 85.1 -> 72.0 | Improved |
| use HRNet-W48 instead of ResNet-50 backbone | CLIFF · 3DPW | MPJPE: 72.0 -> 69.0 | Improved |
| add OneEuro temporal filtering | CLIFF (Res-50) · 3DPW | Accel Error: 24.7 -> 10.6 | Improved |
| add OneEuro temporal filtering | CLIFF (Res-50) · 3DPW | MPJPE: 72.0 -> 74.0 | Hurt |
Later papers that compared with this method
23 later accepted papers report CLIFF as a baseline in their results tables; 18 of them report a better number on most of the results they share with it.
- MobileOcc: A Human-Aware Semantic Occupancy Dataset for Mobile Robots (ECCV 2026 · better on 6 of 6 shared results)
- RAM: Recover Any 3D Human Motion in-the-Wild (CVPR 2026 · better on 1 of 1 shared result)
- VOccl3D: A Video Benchmark Dataset for 3D Human Pose and Shape Estimation under real Occlusions (ICCV 2025 · better on 10 of 10 shared results)
- MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond (CVPR 2025 · better on 2 of 2 shared results)
- CoMotion: Concurrent Multi-person 3D Motion (ICLR 2025 · better on 2 of 2 shared results)
- HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-Body Mesh Recovery (TPAMI 2025 · better on 2 of 2 shared results)
- GenHMR: Generative Human Mesh Recovery (AAAI 2025 · better on 1 of 1 shared result)
- PI-HMR: Towards Robust In-bed Temporal Human Shape Reconstruction with Contact Pressure Sensing (CVPR 2025 · better on 1 of 1 shared result)
15 more not listed.
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- A Simple yet Effective Baseline for 3D Human Pose Estimation (ICCV 2017 · similarity 0.88)
- PandaPose: 3D Human Pose Lifting from a Single Image via Propagating 2D Pose Prior to 3D Anchor Space (NeurIPS 2025 · similarity 0.87)
- ProbPose: A Probabilistic Approach to 2D Human Pose Estimation (CVPR 2025 · similarity 0.87)
- Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation (NeurIPS 2024 · similarity 0.87)
- SelfPose3d: Self-Supervised Multi-Person Multi-View 3d Pose Estimation (CVPR 2024 · similarity 0.86)
- FreeMan: Towards Benchmarking 3D Human Pose Estimation under Real-World Conditions (CVPR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
